Skip to content
Extra Form
Abstract The block erection using a crane such as a gantry crane and a floating crane is one of the most important processes in the production of ships and offshore structures. To mount the block with the correct position and angle, it is important to control the block accurately not to occur the unexpected movement like rotation. However, it is difficult to apply the existing control theory to the block lifting operation because the movement of the block is controlled indirectly with the control of various objects such as the crane and wire ropes. To solve this problem, a block control method based on deep reinforcement learning is proposed in this study. The proposed method is easier to control the block with wire ropes and to consider irregular external force than existing control theory. In this study, the angle and angular velocity of the lifting block and the hoisting speed of each wire rope that can affect the motion of the block are set as states of reinforcement learning, and the hoisting speed that is the control object is set as an action of reinforcement learning. The reward function of reinforcement learning is designed to increase when the angle of the block decrease and the speed of the block is close to the target speed. In this study the policy gradient method which is a kind of policy-based methods of deep reinforcement learning is used to solve the problem with continuous states and action. To check the applicability and feasibility of the proposed method, The block lifting simulation is performed using the existing control theory and the proposed method. We compared the proposed method with the existing control theory. The result shows that the proposed method can minimize the motion of the lifting block more effectively than the existing control theory.
Publication Date 2019-08-28

Do-Hyun Chun, Myung-Il Roh, Hye-Won Lee, Seung-Ho Ham, "A Crane Movement Control for Stability of Block Erection Based on Deep Reinforcement Learning", MIM(International Federation of Automatic Control) 2019, Berlin, Germany, 2019.08.28-30


List of Articles
번호 분류 제목 Publication Date
519 Domestic Conference 임중현, 이상욱, 노명일, 이규열, "다면체를 이용한 선박 구획 계산에 관한 연구", 1999년도 대한조선학회 춘계학술발표회, 거제, pp. 103-106, 1999.04.22-23 file 1999-04-22
518 Domestic Conference 노명일, 이규열, "협동 최적화 방법에 의한 다분야 최적화 기법에 관한 연구", 1999년도 대한조선학회 추계학술발표회, 대전, pp. 159-164, 1999.11.11-12 file 1999-11-11
517 Domestic Conference 노명일, 이규열, "협동 최적화 접근방법에 의한 다분야 최적 설계에 관한 연구", 2000년도 한국CAD/CAM학회 학술발표회, 서울, pp. 163-170, 2000.02.11 file 2000-02-11
516 International Conference Kyu-Yeul Lee, Seon-Ho Cho, Myung-Il Roh, "An Efficient Global-Local Hybrid Optimization Method Using Design Sensitivity Analysis", Proceedings of OptiCon 2000, Newport Beach, USA, pp. 1-13, 2000.10.26-27 file 2000-10-26
515 Domestic Conference 한성남, 이규열, 노명일, "개선된 유전자 알고리즘을 이용한 최적 공간 배치 설계에 관한 연구", 2001년도 한국CAD/CAM학회 학술발표회, 서울, pp. 253-260, 2001.02.09 file 2001-02-09
514 Domestic Conference 이규열, 노명일, "Hybrid Optimization 방법과 CORBA를 이용한 다분야 최적 설계에 관한 연구", 2001년도 한국항공우주학회 학술발표회, 진주, pp. 590-593, 2001.04.14 file 2001-04-14
513 Domestic Conference 한성남, 노명일, 이규열, "최적 공간 배치 설계를 위한 개선된 유전자 알고리즘에 관한 연구", 2001년도 한국경영과학회/대한산업공학회 춘계학술발표회, 양양, pp. 239, 2001.04.27-28 file 2001-04-27
512 International Conference Kyu-Yeul Lee, Myung-Il Roh, Hang-Soon Choi, Woo-Jae Seong, "Development of Hybrid Optimization Method and Its Application to Ship Design Optimization", Proceedings of Pacific 2002 International Maritime Conference, Sydney, Australia, 2002.01.29-31 file 2002-01-29
511 Domestic Conference 이원준, 이규열, 권오환, 노명일, "의미론적 제품 데이터 모델 기반 초기 선체 구조 CAD 시스템 개발", 2002년도 한국CAD/CAM학회 학술발표회, 서울, pp. 75-87, 2002.01.30 file 2002-01-30
510 Domestic Conference 정혁수, 이규열, 노명일, "다중 갑판을 고려한 함정의 최적 격실 배치 설계에 관한 연구", 2002년도 대한조선학회 춘계학술발표회, 부산, pp. 71-78, 2002.04.18-19 file 2002-04-18
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 ... 52 Next
/ 52

Powered by Xpress Engine / Designed by Sketchbook

sketchbook5, 스케치북5

sketchbook5, 스케치북5

나눔글꼴 설치 안내


이 PC에는 나눔글꼴이 설치되어 있지 않습니다.

이 사이트를 나눔글꼴로 보기 위해서는
나눔글꼴을 설치해야 합니다.

설치 취소